most of them try to argue serving ads and tracking is `legitimate interest`, which you have to disable manually

> most of them

I'm also grumpy about lots of this, but most? Can you point at any data that support this?

They had two dedicated legions garrisoned in Rome, who did not participate in Cannae, from what I read (not sure)

Hannibal was basically in a hostile land, without proper logistics support. There was no way that he can stay still and lay siege, only way he was able to survive so far was his ability to stay mobile and live off the land.

In case of siege, the Romans would not need to fight, they could simply wait until his army slowly died from attrition.

When you are riding the bike in the city, the light is not for you to see things, it is for others to see and notice you.

Can't emphasise that enough. Especially if you're into black clothing and have a black bike.

"This showed that for cars DRL reduces the number of daytime injury crashes by 3-12%. The effect on fatal crashes can be estimated as somewhat greater (-15%)."

https://swov.nl/system/files/publication-downloads/fs_drl_ar...

This is about cars/motorcycles and daytime, but it certainly applies to any moving vehicle at any time...

When driving, I love those bicyclists that have a blinking rear light btw. Can't overlook them.

which version of httpx?

same as in dependencies = [ # "httpx", # ]

the current one by default

> For example, I was able to use a version with boto3 to answer questions about an AWS cluster that took multiple API calls.

isn't that very dangerous? The LLM may do anything, e.g. create resources, delete resources, change configuration etc

It seems like a very similar issue arises with the "natural language query" problem for database systems. My best guess at a solution in that domain is to restrict the interface. Allow the LLM to generate whatever SQL it wants, but parse that SQL with a restricted grammar that only allows a "safe" (e.g. non-mutating) subset of SQL before actually issuing queries to the database. Then figure out (somehow) how to close the loop on error handling when the LLM violates the contract (e.g. generates a query which doesn't parse).

Then of course there's the whole UX problem of even when you restrict the interface to safe queries, the LLM may still generate queries which are completely incorrect. The best idea I can come up with there is to dump the query text to an editor where the user can review it for correctness.

So it's not really "natural language queries" more like "natural language SQL generation" which is a completely different thing and absolutely should not be marketed as the former.

People bring up this concept as a way to make systems "more friendly to novice users" which tbh makes me a little uncomfortable, because it seems like just a huge footgun. I'd rather have novice users struggle a bit and become less novice, than to encourage them to run and implicitly trust queries which are likely incorrect.

So it's a bit difficult to tell how much value is added here over some basic intellisense style autocomplete.

Looking to the world of "real tools" like hammers and saws, we don't see "novice hammers" or "novice saws". The tool is the tool, and your skill using it grows as you use it more. It seems like a bit of a boondoggle to try to guess what might be good for a novice and orient your entire product experience around that, rather than simply making a tool that's good for experts doing real work and trusting that the novices will put in the effort to build expertise.

It makes for a flashy demo, though.

Only if you give it unfettered accesss. AWS has an API called AssumeRole which can generate short-lived credentials with a specifically scoped set of permissions, which I use instead.

Good thing is it is illegal to have video footage of public land where I live. You can only monitor exactly the entrance or your private land.

Parquet files being immutable is not a bug, it is a feature. That is how you accomplish good compression and keep the columnar data organized.

Yes, it is not useful for continuous writes and updates, but it is not what it is designed for. Use a database (e.g. SQLite just like you suggested) if you want to ingest real time/streaming data.

If you play long enough, you always lose all of your money.

The financial transactions are also shared by the both sides, EU can also request data from US, as clearly stated in the document.

Both document clearly define the uses cases that are applicable for the data sharing, and the second document linked by you also explicitly states that US has to put same effort to provide same capabilities to EU as well.